detr_finetuned_cppe5_poisoned

This model is a fine-tuned version of Jesse020202/cppe5_setup_on_roadsign_test on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4114

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	107	1.6085
No log	2.0	214	1.5592
No log	3.0	321	1.5740
No log	4.0	428	1.5883
1.3843	5.0	535	1.5184
1.3843	6.0	642	1.5885
1.3843	7.0	749	1.5189
1.3843	8.0	856	1.5144
1.3843	9.0	963	1.4986
1.3063	10.0	1070	1.4738
1.3063	11.0	1177	1.4630
1.3063	12.0	1284	1.4525
1.3063	13.0	1391	1.4257
1.3063	14.0	1498	1.4206
1.2038	15.0	1605	1.4078
1.2038	16.0	1712	1.4127
1.2038	17.0	1819	1.4153
1.2038	18.0	1926	1.4113
1.1309	19.0	2033	1.4116
1.1309	20.0	2140	1.4114

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0
• Datasets 4.1.1
• Tokenizers 0.22.1